INDEX

Explanations

phrases that indicate a component or element of a larger whole

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ModelExpression

-0.88

$.}

-0.72

).}

-0.71

+#+#

-0.70

 Humph

-0.70

 saites

-0.70

 seamen

-0.69

Personensuche

-0.69

IntoConstraints

-0.68

 Beowulf

-0.68

POSITIVE LOGITS

 part

1.21

part

0.95

 onderdeel

0.91

 ramach

0.87

Part

0.82

 PART

0.80

 parte

0.79

 Part

0.78

 Bestandteil

0.78

částí

0.76

Activations Density 0.074%

phrases that indicate a component or element of a larger whole

No Comments

No Known Activations